# Explaining Trained Neural Networks with Semantic Web Technologies: First Steps

arXiv: https://arxiv.org/abs/1710.04324 · HTML: https://mlsanity.com/paper/1710.04324/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2017.

## Built on by (most cited first, 13 of 13)

- [Neuro-Symbolic Artificial Intelligence: Current Trends](https://mlsanity.com/paper/2105.05330/) (2021)
- [Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases](https://mlsanity.com/paper/2102.11965/) (2021)
- [Learning Concept Lengths Accelerates Concept Learning in ALC](https://mlsanity.com/paper/2107.04911/) (2021)
- [Towards Human-Compatible XAI: Explaining Data Differentials with Concept Induction over Background Knowledge](https://mlsanity.com/paper/2209.13710/) (2022)
- [On the Value of Labeled Data and Symbolic Methods for Hidden Neuron Activation Analysis](https://mlsanity.com/paper/2404.13567/) (2024)
- [Combining Sub-Symbolic and Symbolic Methods for Explainability](https://mlsanity.com/paper/2112.01844/) (2021)
- [Computing Rule-Based Explanations of Machine Learning Classifiers using Knowledge Graphs](https://mlsanity.com/paper/2202.03971/) (2022)
- [Explaining Deep Learning Hidden Neuron Activations using Concept Induction](https://mlsanity.com/paper/2301.09611/) (2023)
- [Understanding CNN Hidden Neuron Activations Using Structured Background Knowledge and Deductive Reasoning](https://mlsanity.com/paper/2308.03999/) (2023)
- [Requirements for Explainability and Acceptance of Artificial Intelligence in Collaborative Work](https://mlsanity.com/paper/2306.15394/) (2023)
- [Error-margin Analysis for Hidden Neuron Activation Labels](https://mlsanity.com/paper/2405.09580/) (2024)
- [A Dynamic Data Driven Approach for Explainable Scene Understanding](https://mlsanity.com/paper/2206.09089/) (2022)
- [What can knowledge graph alignment gain with Neuro-Symbolic learning approaches?](https://mlsanity.com/paper/2310.07417/) (2023)

## Abstract (arXiv)

The ever increasing prevalence of publicly available structured data on the World Wide Web enables new applications in a variety of domains. In this paper, we provide a conceptual approach that leverages such data in order to explain the input-output behavior of trained artificial neural networks. We apply existing Semantic Web technologies in order to provide an experimental proof of concept.